Make Data Treasures Usable for Medicine

Young researchers in Karlsruhe and Heidelberg are to develop new diagnostic and therapeutic procedures based on large amounts of data

data treasures
The "supercomputer" of the KIT quickly processes enormous amounts of data as they are now to be used for medical research. (Photo: Markus Breig, KIT)

In the research, diagnosis and treatment of diseases, vast amounts of data are generated. To systematically comb through these can create new knowledge for the diagnosis and treatment of conditions such as cancer. The Karlsruhe Institute of Technology (KIT), the German Cancer Research Center (DKFZ) and the University of Heidelberg are now working together to train young researchers working at the interface of health research, life sciences and data science. Twelve million euros are ready for it.

At the newly founded Helmholtz Information & Data Science School for Health (HIDSS4Health), junior scientists are to be trained in a joint doctoral program of the three institutions for working with the data volumes arising in the health sector. They will learn to develop new methods for diagnosis and therapy based on the analysis of huge amounts of data.

For example, machine learning and other data-driven methods could help interpreting images from computed tomography or magnetic resonance imaging, as Professor Ralf Mikut of KIT‘s Institute for Automation and Applied Computer Science calls an example of digital transformation in healthcare. “To evaluate such recordings, a doctor needs a lot of experience,” says Mikut, who coordinates the doctoral program at KIT. “Here, such algorithms could do preparatory work by, for example, directing the attention of the physician to certain regions.” There are also potential applications of methods and technologies in the field of data-driven radiotherapy.

“Information on the extent of tumors is always associated with certain uncertainties, these could be considered in future in the treatment planning and thus achieve better results,” says Klaus Maier-Hein of the German Cancer Research Center. Last but not least, computer-based methods such as simulators or robot-assisted surgical trainers could be used in medical education, according to Katja Mombaur from the Institute of Computer Engineering at the University of Heidelberg.

All in all, jobs will be created for 35 to 40 doctoral candidates working across groups at the three locations in Heidelberg and Karlsruhe. “The offer is aimed at applicants with a background in data science who are interested in medical topics,” says Mikut. KIT invests over three million euros; DKFZ and the University of Heidelberg are once again investing roughly the same amount. Nearly six million euros come from the Helmholtz Association of German Research Centers.

In the future, the Helmholtz Association is investing 35 million euros annually in the digitization of research and is establishing four new types of platforms. With the participation of KIT and the DKFZ one of the platforms emerged: the Helmholtz Information & Data Science Academy (HIDA). Five Helmholtz Information & Data Science Schools (HIDSS) are merging under the HIDA umbrella.

Source : Karlsruhe Institute of Technology (KIT)